{"id":101,"date":"2026-04-08T04:12:24","date_gmt":"2026-04-08T04:12:24","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/101\/"},"modified":"2026-04-08T04:12:24","modified_gmt":"2026-04-08T04:12:24","slug":"bostons-cio-wants-the-public-and-other-city-governments-to-use-his-open-source-agentic-ai-tools","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/101\/","title":{"rendered":"Boston’s CIO wants the public \u2014 and other city governments \u2014 to use his open-source agentic AI tools"},"content":{"rendered":"

Boston\u2019s chief information officer, Santiago Garces, is betting on agentic artificial intelligence to transform the city\u2019s open data into usable insights, and not just for data analysts, but for residents who are trying to better understand their communities.<\/p>\n

To make that vision real, the city in October launched a model context protocol, or MCP, server \u2014 an Anthropic-built software layer that allows a Claude AI model to securely interact with data sources, like Boston\u2019s open data portal. More recently, Garces built a set of open-source \u201cskills,\u201d Anthropic\u2019s term for workflow templates, which run on the city\u2019s MCP server. Garces said he thinks of each skill as a different AI \u201cagent.\u201d Each skill, or agent, sets up a complex analytical workflow that can produce formatted tables and plain language to answer various questions.<\/p>\n

Developed with Bloomberg Philanthropies<\/a> and the Abdul Latif Jameel Poverty Action Lab,<\/a> or J-PAL, at the Massachusetts Institute of Technology, Garces said the tools are designed to let anyone access and analyze city data, with the goal of expanding transparency, improving policymaking and broadening who can participate in data-driven decision-making.<\/p>\n

The MCP server, Garces said, acts as a foundational layer that allows the AI agents to interface with Boston\u2019s open data system<\/a>, which includes datasets on things like city infrastructure and public services. There are datasets on property records, trash schedules, snow emergency routes, public-school locations, tree canopy assessments, building permits and 311 service requests, such as pothole tracking.<\/p>\n

\"SantiagoSantiago Garces, CIO of Boston, Massachusetts. (City of Boston)<\/p>\n

Previously, a city data analyst may have had to download spreadsheets and then upload them into a chatbot to perform an analysis. But this process, Garces noted, was less secure, as it produced copies of data along the way, and it was less accurate because the data might be outdated \u2014 it\u2019s just generally \u201cmore of a pain.\u201d<\/p>\n

Garces said it took some time to equip the MCP server to handle more complicated questions, but that it now gives AI agents a safe and structured way to query the city\u2019s data. However, this function alone was not enough \u2014 the server needed context. Garces said that where the benefits of agentic AI became clear.<\/p>\n

\u201cThe best people that do data analysis and policymaking kind of go through a certain workflow, or a set of workflows. So this is where terms like agentic AI come into play,\u201d he said. \u201cAll an agent, or a set of agents, are is like a collection of things that work in a particular way, trying to solve a piece of the puzzle, if you will.\u201d<\/p>\n

These agents, he said, are guided with code written in plain language, step\u2011by\u2011step, on a number of tasks, such as how to frame a problem, decide what to compare, interrogate the numbers and turn them into clear findings so the system can answer complex questions instead of just spitting out raw statistics. They are informed via the habits of a good policy analyst, Garces added. <\/p>\n

\u201cAll I did was take these really large bodies of work, like the Bloomberg Center for Public Innovation has like this handbook for public innovation. It\u2019s like 50 pages, and it shows you how to train a person how to do this thing. I just condensed it to these files and Claude now follows that path,\u201d he said. \u201cThese are the way that like really good data analysts and good policy analysts do things, we were trained to follow these kind of patterns of how to solve problems. It\u2019s just that now I can push my AI tools to follow these recipes.\u201d<\/p>\n

One of the agents, which Garces called the \u201corchestrator,\u201d reads the users\u2019 questions and decides which of the other agents to activate and in what order. The orchestrator routes the question through the five agents \u2014 problem\u2011framing, analysis, communication, benchmarking or performance management \u2014 passing the output of each onto the next so the AI behaves more like a coordinated team of analysts, rather than a single chatbot.<\/p>\n

\u201cThe goal here was, Can I level the playing field?\u201d Garces said. \u201cCan I have more people, both inside City Hall, and residents, be able to access kind of like that same level of thinking, if you will, like that same level of analysis that right now only like the mayor or like a department head would get access to, because you need access to a fairly sophisticated data or policy analyst.\u201d<\/p>\n

The skills, or agents, are available on Garces\u2019 GitHub<\/a>, but he plans to turn the technology into what he described as a shared, civic infrastructure. He said these agentic skills are just the beginning of what will be possible. In the coming months, Garces said, he plans to make Boston\u2019s MCP server publicly accessible, so that anyone can use their own AI tools to draw on the city\u2019s data to get answers to complex questions.<\/p>\n

Garces is encouraging other cities to\u00a0adapt the agents for their own open data portals. He said they\u2019re compatible with the three largest open data platforms so that they can complete cross\u2011city comparisons. (The three most widely adopted open data platforms are developed by Tyler Technologies, Esri and Opendatasoft.)<\/p>\n

In Boston, Garces said, his focus is getting\u00a0every city employee who\u2019s completed responsible\u2011AI training\u00a0access to the agents, so frontline staff can do \u201cmayor\u2011level\u201d analysis without needing to wait on a data analyst.<\/p>\n

\u201cOur hope is then trying to figure out, how is it that we can get every city employee access to these tools? How is it that we can make sure that our constituents have access to these tools?\u201d he said. \u201cBecause we just think that it can really help us have better conversations using the same data and the same facts as the ground truth, and it just, hopefully, helps us solve more complicated problems together in a way that is more civil, that is more interesting.\u201d<\/p>\n

\t\t\t\t\t\"Keely<\/p>\n

\n\t\t\tWritten by Keely Quinlan
\n\t\t\tKeely Quinlan reports on privacy and digital government for StateScoop. She was an investigative news reporter with Clarksville Now in Tennessee, where she resides, and her coverage included local crimes, courts, public education and public health. Her work has appeared in Teen Vogue, Stereogum and other outlets. She earned her bachelor\u2019s in journalism and master\u2019s in social and cultural analysis from New York University.\t\t<\/p>\n","protected":false},"excerpt":{"rendered":"Boston\u2019s chief information officer, Santiago Garces, is betting on agentic artificial intelligence to transform the city\u2019s open data…\n","protected":false},"author":2,"featured_media":102,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[179,24,53,25,111,180,181,182,183,184,185,186],"class_list":{"0":"post-101","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-ai","8":"tag-agentic-ai","9":"tag-ai","10":"tag-anthropic","11":"tag-artificial-intelligence","12":"tag-artificial-intelligence-ai","13":"tag-bloomberg-philanthropies","14":"tag-boston","15":"tag-claude","16":"tag-data-analytics","17":"tag-santiago-garces","18":"tag-state-local-news","19":"tag-tech-news"},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/101","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=101"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/101\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/102"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=101"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=101"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=101"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}